| |
| <!DOCTYPE html> |
| <!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]--> |
| <!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8"> <![endif]--> |
| <!--[if IE 8]> <html class="no-js lt-ie9"> <![endif]--> |
| <!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]--> |
| <head> |
| <meta charset="utf-8"> |
| <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>Dimensionality Reduction - RDD-based API - Spark 3.5.3 Documentation</title> |
| |
| |
| |
| |
| |
| <link rel="stylesheet" href="css/bootstrap.min.css"> |
| <link rel="preconnect" href="https://fonts.googleapis.com"> |
| <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> |
| <link href="https://fonts.googleapis.com/css2?family=DM+Sans:ital,wght@0,400;0,500;0,700;1,400;1,500;1,700&Courier+Prime:wght@400;700&display=swap" rel="stylesheet"> |
| <link href="css/custom.css" rel="stylesheet"> |
| <script src="js/vendor/modernizr-2.6.1-respond-1.1.0.min.js"></script> |
| |
| <link rel="stylesheet" href="css/pygments-default.css"> |
| <link rel="stylesheet" href="css/docsearch.min.css" /> |
| <link rel="stylesheet" href="css/docsearch.css"> |
| |
| |
| <!-- Matomo --> |
| <script> |
| var _paq = window._paq = window._paq || []; |
| /* tracker methods like "setCustomDimension" should be called before "trackPageView" */ |
| _paq.push(["disableCookies"]); |
| _paq.push(['trackPageView']); |
| _paq.push(['enableLinkTracking']); |
| (function() { |
| var u="https://analytics.apache.org/"; |
| _paq.push(['setTrackerUrl', u+'matomo.php']); |
| _paq.push(['setSiteId', '40']); |
| var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0]; |
| g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s); |
| })(); |
| </script> |
| <!-- End Matomo Code --> |
| |
| |
| </head> |
| <body class="global"> |
| <!--[if lt IE 7]> |
| <p class="chromeframe">You are using an outdated browser. <a href="https://browsehappy.com/">Upgrade your browser today</a> or <a href="http://www.google.com/chromeframe/?redirect=true">install Google Chrome Frame</a> to better experience this site.</p> |
| <![endif]--> |
| |
| <!-- This code is taken from http://twitter.github.com/bootstrap/examples/hero.html --> |
| |
| <nav class="navbar navbar-expand-lg navbar-dark p-0 px-4 fixed-top" style="background: #1d6890;" id="topbar"> |
| <div class="navbar-brand"><a href="index.html"> |
| <img src="img/spark-logo-rev.svg" width="141" height="72"/></a><span class="version">3.5.3</span> |
| </div> |
| <button class="navbar-toggler" type="button" data-toggle="collapse" |
| data-target="#navbarCollapse" aria-controls="navbarCollapse" |
| aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| <div class="collapse navbar-collapse" id="navbarCollapse"> |
| <ul class="navbar-nav me-auto"> |
| <li class="nav-item"><a href="index.html" class="nav-link">Overview</a></li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarQuickStart" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Programming Guides</a> |
| <div class="dropdown-menu" aria-labelledby="navbarQuickStart"> |
| <a class="dropdown-item" href="quick-start.html">Quick Start</a> |
| <a class="dropdown-item" href="rdd-programming-guide.html">RDDs, Accumulators, Broadcasts Vars</a> |
| <a class="dropdown-item" href="sql-programming-guide.html">SQL, DataFrames, and Datasets</a> |
| <a class="dropdown-item" href="structured-streaming-programming-guide.html">Structured Streaming</a> |
| <a class="dropdown-item" href="streaming-programming-guide.html">Spark Streaming (DStreams)</a> |
| <a class="dropdown-item" href="ml-guide.html">MLlib (Machine Learning)</a> |
| <a class="dropdown-item" href="graphx-programming-guide.html">GraphX (Graph Processing)</a> |
| <a class="dropdown-item" href="sparkr.html">SparkR (R on Spark)</a> |
| <a class="dropdown-item" href="api/python/getting_started/index.html">PySpark (Python on Spark)</a> |
| </div> |
| </li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarAPIDocs" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">API Docs</a> |
| <div class="dropdown-menu" aria-labelledby="navbarAPIDocs"> |
| <a class="dropdown-item" href="api/scala/org/apache/spark/index.html">Scala</a> |
| <a class="dropdown-item" href="api/java/index.html">Java</a> |
| <a class="dropdown-item" href="api/python/index.html">Python</a> |
| <a class="dropdown-item" href="api/R/index.html">R</a> |
| <a class="dropdown-item" href="api/sql/index.html">SQL, Built-in Functions</a> |
| </div> |
| </li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarDeploying" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Deploying</a> |
| <div class="dropdown-menu" aria-labelledby="navbarDeploying"> |
| <a class="dropdown-item" href="cluster-overview.html">Overview</a> |
| <a class="dropdown-item" href="submitting-applications.html">Submitting Applications</a> |
| <div class="dropdown-divider"></div> |
| <a class="dropdown-item" href="spark-standalone.html">Spark Standalone</a> |
| <a class="dropdown-item" href="running-on-mesos.html">Mesos</a> |
| <a class="dropdown-item" href="running-on-yarn.html">YARN</a> |
| <a class="dropdown-item" href="running-on-kubernetes.html">Kubernetes</a> |
| </div> |
| </li> |
| |
| <li class="nav-item dropdown"> |
| <a href="#" class="nav-link dropdown-toggle" id="navbarMore" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">More</a> |
| <div class="dropdown-menu" aria-labelledby="navbarMore"> |
| <a class="dropdown-item" href="configuration.html">Configuration</a> |
| <a class="dropdown-item" href="monitoring.html">Monitoring</a> |
| <a class="dropdown-item" href="tuning.html">Tuning Guide</a> |
| <a class="dropdown-item" href="job-scheduling.html">Job Scheduling</a> |
| <a class="dropdown-item" href="security.html">Security</a> |
| <a class="dropdown-item" href="hardware-provisioning.html">Hardware Provisioning</a> |
| <a class="dropdown-item" href="migration-guide.html">Migration Guide</a> |
| <div class="dropdown-divider"></div> |
| <a class="dropdown-item" href="building-spark.html">Building Spark</a> |
| <a class="dropdown-item" href="https://spark.apache.org/contributing.html">Contributing to Spark</a> |
| <a class="dropdown-item" href="https://spark.apache.org/third-party-projects.html">Third Party Projects</a> |
| </div> |
| </li> |
| |
| <li class="nav-item"> |
| <input type="text" id="docsearch-input" placeholder="Search the docs…"> |
| </li> |
| </ul> |
| <!--<span class="navbar-text navbar-right"><span class="version-text">v3.5.3</span></span>--> |
| </div> |
| </nav> |
| |
| |
| |
| <div class="container"> |
| |
| |
| |
| <div class="left-menu-wrapper"> |
| <div class="left-menu"> |
| <h3><a href="ml-guide.html">MLlib: Main Guide</a></h3> |
| |
| <ul> |
| |
| <li> |
| <a href="ml-statistics.html"> |
| |
| Basic statistics |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-datasource.html"> |
| |
| Data sources |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-pipeline.html"> |
| |
| Pipelines |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-features.html"> |
| |
| Extracting, transforming and selecting features |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-classification-regression.html"> |
| |
| Classification and Regression |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-clustering.html"> |
| |
| Clustering |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-collaborative-filtering.html"> |
| |
| Collaborative filtering |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-frequent-pattern-mining.html"> |
| |
| Frequent Pattern Mining |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-tuning.html"> |
| |
| Model selection and tuning |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="ml-advanced.html"> |
| |
| Advanced topics |
| |
| </a> |
| </li> |
| |
| |
| |
| </ul> |
| |
| <h3><a href="mllib-guide.html">MLlib: RDD-based API Guide</a></h3> |
| |
| <ul> |
| |
| <li> |
| <a href="mllib-data-types.html"> |
| |
| Data types |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-statistics.html"> |
| |
| Basic statistics |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-classification-regression.html"> |
| |
| Classification and regression |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-collaborative-filtering.html"> |
| |
| Collaborative filtering |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-clustering.html"> |
| |
| Clustering |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-dimensionality-reduction.html"> |
| |
| Dimensionality reduction |
| |
| </a> |
| </li> |
| |
| |
| |
| <ul> |
| |
| <li> |
| <a href="mllib-dimensionality-reduction.html#singular-value-decomposition-svd"> |
| |
| singular value decomposition (SVD) |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-dimensionality-reduction.html#principal-component-analysis-pca"> |
| |
| principal component analysis (PCA) |
| |
| </a> |
| </li> |
| |
| |
| |
| </ul> |
| |
| |
| |
| <li> |
| <a href="mllib-feature-extraction.html"> |
| |
| Feature extraction and transformation |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-frequent-pattern-mining.html"> |
| |
| Frequent pattern mining |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-evaluation-metrics.html"> |
| |
| Evaluation metrics |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-pmml-model-export.html"> |
| |
| PMML model export |
| |
| </a> |
| </li> |
| |
| |
| |
| <li> |
| <a href="mllib-optimization.html"> |
| |
| Optimization (developer) |
| |
| </a> |
| </li> |
| |
| |
| |
| </ul> |
| |
| </div> |
| </div> |
| |
| <input id="nav-trigger" class="nav-trigger" checked type="checkbox"> |
| <label for="nav-trigger"></label> |
| <div class="content-with-sidebar mr-3" id="content"> |
| |
| <h1 class="title">Dimensionality Reduction - RDD-based API</h1> |
| |
| |
| <ul id="markdown-toc"> |
| <li><a href="#singular-value-decomposition-svd" id="markdown-toc-singular-value-decomposition-svd">Singular value decomposition (SVD)</a> <ul> |
| <li><a href="#performance" id="markdown-toc-performance">Performance</a></li> |
| <li><a href="#svd-example" id="markdown-toc-svd-example">SVD Example</a></li> |
| </ul> |
| </li> |
| <li><a href="#principal-component-analysis-pca" id="markdown-toc-principal-component-analysis-pca">Principal component analysis (PCA)</a></li> |
| </ul> |
| |
| <p><a href="http://en.wikipedia.org/wiki/Dimensionality_reduction">Dimensionality reduction</a> is the process |
| of reducing the number of variables under consideration. |
| It can be used to extract latent features from raw and noisy features |
| or compress data while maintaining the structure. |
| <code class="language-plaintext highlighter-rouge">spark.mllib</code> provides support for dimensionality reduction on the <a href="mllib-data-types.html#rowmatrix">RowMatrix</a> class.</p> |
| |
| <h2 id="singular-value-decomposition-svd">Singular value decomposition (SVD)</h2> |
| |
| <p><a href="http://en.wikipedia.org/wiki/Singular_value_decomposition">Singular value decomposition (SVD)</a> |
| factorizes a matrix into three matrices: $U$, $\Sigma$, and $V$ such that</p> |
| |
| <p><code class="language-plaintext highlighter-rouge">\[ |
| A = U \Sigma V^T, |
| \]</code></p> |
| |
| <p>where</p> |
| |
| <ul> |
| <li>$U$ is an orthonormal matrix, whose columns are called left singular vectors,</li> |
| <li>$\Sigma$ is a diagonal matrix with non-negative diagonals in descending order, |
| whose diagonals are called singular values,</li> |
| <li>$V$ is an orthonormal matrix, whose columns are called right singular vectors.</li> |
| </ul> |
| |
| <p>For large matrices, usually we don’t need the complete factorization but only the top singular |
| values and its associated singular vectors. This can save storage, de-noise |
| and recover the low-rank structure of the matrix.</p> |
| |
| <p>If we keep the top $k$ singular values, then the dimensions of the resulting low-rank matrix will be:</p> |
| |
| <ul> |
| <li><code class="language-plaintext highlighter-rouge">$U$</code>: <code class="language-plaintext highlighter-rouge">$m \times k$</code>,</li> |
| <li><code class="language-plaintext highlighter-rouge">$\Sigma$</code>: <code class="language-plaintext highlighter-rouge">$k \times k$</code>,</li> |
| <li><code class="language-plaintext highlighter-rouge">$V$</code>: <code class="language-plaintext highlighter-rouge">$n \times k$</code>.</li> |
| </ul> |
| |
| <h3 id="performance">Performance</h3> |
| <p>We assume $n$ is smaller than $m$. The singular values and the right singular vectors are derived |
| from the eigenvalues and the eigenvectors of the Gramian matrix $A^T A$. The matrix |
| storing the left singular vectors $U$, is computed via matrix multiplication as |
| $U = A (V S^{-1})$, if requested by the user via the computeU parameter. |
| The actual method to use is determined automatically based on the computational cost:</p> |
| |
| <ul> |
| <li>If $n$ is small ($n < 100$) or $k$ is large compared with $n$ ($k > n / 2$), we compute the Gramian matrix |
| first and then compute its top eigenvalues and eigenvectors locally on the driver. |
| This requires a single pass with $O(n^2)$ storage on each executor and on the driver, and |
| $O(n^2 k)$ time on the driver.</li> |
| <li>Otherwise, we compute $(A^T A) v$ in a distributive way and send it to |
| <a href="http://www.caam.rice.edu/software/ARPACK/">ARPACK</a> to |
| compute $(A^T A)$’s top eigenvalues and eigenvectors on the driver node. This requires $O(k)$ |
| passes, $O(n)$ storage on each executor, and $O(n k)$ storage on the driver.</li> |
| </ul> |
| |
| <h3 id="svd-example">SVD Example</h3> |
| |
| <p><code class="language-plaintext highlighter-rouge">spark.mllib</code> provides SVD functionality to row-oriented matrices, provided in the |
| <a href="mllib-data-types.html#rowmatrix">RowMatrix</a> class.</p> |
| |
| <div class="codetabs"> |
| |
| <div data-lang="python"> |
| <p>Refer to the <a href="api/python/reference/api/pyspark.mllib.linalg.distributed.SingularValueDecomposition.html"><code class="language-plaintext highlighter-rouge">SingularValueDecomposition</code> Python docs</a> for details on the API.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">Vectors</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.linalg.distributed</span> <span class="kn">import</span> <span class="n">RowMatrix</span> |
| |
| <span class="n">rows</span> <span class="o">=</span> <span class="n">sc</span><span class="p">.</span><span class="n">parallelize</span><span class="p">([</span> |
| <span class="n">Vectors</span><span class="p">.</span><span class="n">sparse</span><span class="p">(</span><span class="mi">5</span><span class="p">,</span> <span class="p">{</span><span class="mi">1</span><span class="p">:</span> <span class="mf">1.0</span><span class="p">,</span> <span class="mi">3</span><span class="p">:</span> <span class="mf">7.0</span><span class="p">}),</span> |
| <span class="n">Vectors</span><span class="p">.</span><span class="n">dense</span><span class="p">(</span><span class="mf">2.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">,</span> <span class="mf">4.0</span><span class="p">,</span> <span class="mf">5.0</span><span class="p">),</span> |
| <span class="n">Vectors</span><span class="p">.</span><span class="n">dense</span><span class="p">(</span><span class="mf">4.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="mf">6.0</span><span class="p">,</span> <span class="mf">7.0</span><span class="p">)</span> |
| <span class="p">])</span> |
| |
| <span class="n">mat</span> <span class="o">=</span> <span class="n">RowMatrix</span><span class="p">(</span><span class="n">rows</span><span class="p">)</span> |
| |
| <span class="c1"># Compute the top 5 singular values and corresponding singular vectors. |
| </span><span class="n">svd</span> <span class="o">=</span> <span class="n">mat</span><span class="p">.</span><span class="n">computeSVD</span><span class="p">(</span><span class="mi">5</span><span class="p">,</span> <span class="n">computeU</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span> |
| <span class="n">U</span> <span class="o">=</span> <span class="n">svd</span><span class="p">.</span><span class="n">U</span> <span class="c1"># The U factor is a RowMatrix. |
| </span><span class="n">s</span> <span class="o">=</span> <span class="n">svd</span><span class="p">.</span><span class="n">s</span> <span class="c1"># The singular values are stored in a local dense vector. |
| </span><span class="n">V</span> <span class="o">=</span> <span class="n">svd</span><span class="p">.</span><span class="n">V</span> <span class="c1"># The V factor is a local dense matrix.</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/python/mllib/svd_example.py" in the Spark repo.</small></div> |
| |
| <p>The same code applies to <code class="language-plaintext highlighter-rouge">IndexedRowMatrix</code> if <code class="language-plaintext highlighter-rouge">U</code> is defined as an |
| <code class="language-plaintext highlighter-rouge">IndexedRowMatrix</code>.</p> |
| </div> |
| |
| <div data-lang="scala"> |
| <p>Refer to the <a href="api/scala/org/apache/spark/mllib/linalg/SingularValueDecomposition.html"><code class="language-plaintext highlighter-rouge">SingularValueDecomposition</code> Scala docs</a> for details on the API.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Matrix</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.SingularValueDecomposition</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vector</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.distributed.RowMatrix</span> |
| |
| <span class="k">val</span> <span class="nv">data</span> <span class="k">=</span> <span class="nc">Array</span><span class="o">(</span> |
| <span class="nv">Vectors</span><span class="o">.</span><span class="py">sparse</span><span class="o">(</span><span class="mi">5</span><span class="o">,</span> <span class="nc">Seq</span><span class="o">((</span><span class="mi">1</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">),</span> <span class="o">(</span><span class="mi">3</span><span class="o">,</span> <span class="mf">7.0</span><span class="o">))),</span> |
| <span class="nv">Vectors</span><span class="o">.</span><span class="py">dense</span><span class="o">(</span><span class="mf">2.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">3.0</span><span class="o">,</span> <span class="mf">4.0</span><span class="o">,</span> <span class="mf">5.0</span><span class="o">),</span> |
| <span class="nv">Vectors</span><span class="o">.</span><span class="py">dense</span><span class="o">(</span><span class="mf">4.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">6.0</span><span class="o">,</span> <span class="mf">7.0</span><span class="o">))</span> |
| |
| <span class="k">val</span> <span class="nv">rows</span> <span class="k">=</span> <span class="nv">sc</span><span class="o">.</span><span class="py">parallelize</span><span class="o">(</span><span class="n">data</span><span class="o">)</span> |
| |
| <span class="k">val</span> <span class="nv">mat</span><span class="k">:</span> <span class="kt">RowMatrix</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">RowMatrix</span><span class="o">(</span><span class="n">rows</span><span class="o">)</span> |
| |
| <span class="c1">// Compute the top 5 singular values and corresponding singular vectors.</span> |
| <span class="k">val</span> <span class="nv">svd</span><span class="k">:</span> <span class="kt">SingularValueDecomposition</span><span class="o">[</span><span class="kt">RowMatrix</span>, <span class="kt">Matrix</span><span class="o">]</span> <span class="k">=</span> <span class="nv">mat</span><span class="o">.</span><span class="py">computeSVD</span><span class="o">(</span><span class="mi">5</span><span class="o">,</span> <span class="n">computeU</span> <span class="k">=</span> <span class="kc">true</span><span class="o">)</span> |
| <span class="k">val</span> <span class="nv">U</span><span class="k">:</span> <span class="kt">RowMatrix</span> <span class="o">=</span> <span class="nv">svd</span><span class="o">.</span><span class="py">U</span> <span class="c1">// The U factor is a RowMatrix.</span> |
| <span class="k">val</span> <span class="nv">s</span><span class="k">:</span> <span class="kt">Vector</span> <span class="o">=</span> <span class="nv">svd</span><span class="o">.</span><span class="py">s</span> <span class="c1">// The singular values are stored in a local dense vector.</span> |
| <span class="k">val</span> <span class="nv">V</span><span class="k">:</span> <span class="kt">Matrix</span> <span class="o">=</span> <span class="nv">svd</span><span class="o">.</span><span class="py">V</span> <span class="c1">// The V factor is a local dense matrix.</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/mllib/SVDExample.scala" in the Spark repo.</small></div> |
| |
| <p>The same code applies to <code class="language-plaintext highlighter-rouge">IndexedRowMatrix</code> if <code class="language-plaintext highlighter-rouge">U</code> is defined as an |
| <code class="language-plaintext highlighter-rouge">IndexedRowMatrix</code>.</p> |
| </div> |
| <div data-lang="java"> |
| <p>Refer to the <a href="api/java/org/apache/spark/mllib/linalg/SingularValueDecomposition.html"><code class="language-plaintext highlighter-rouge">SingularValueDecomposition</code> Java docs</a> for details on the API.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">import</span> <span class="nn">java.util.Arrays</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">java.util.List</span><span class="o">;</span> |
| |
| <span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaRDD</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaSparkContext</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Matrix</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.SingularValueDecomposition</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vector</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.distributed.RowMatrix</span><span class="o">;</span> |
| |
| <span class="nc">List</span><span class="o"><</span><span class="nc">Vector</span><span class="o">></span> <span class="n">data</span> <span class="o">=</span> <span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span> |
| <span class="nc">Vectors</span><span class="o">.</span><span class="na">sparse</span><span class="o">(</span><span class="mi">5</span><span class="o">,</span> <span class="k">new</span> <span class="kt">int</span><span class="o">[]</span> <span class="o">{</span><span class="mi">1</span><span class="o">,</span> <span class="mi">3</span><span class="o">},</span> <span class="k">new</span> <span class="kt">double</span><span class="o">[]</span> <span class="o">{</span><span class="mf">1.0</span><span class="o">,</span> <span class="mf">7.0</span><span class="o">}),</span> |
| <span class="nc">Vectors</span><span class="o">.</span><span class="na">dense</span><span class="o">(</span><span class="mf">2.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">3.0</span><span class="o">,</span> <span class="mf">4.0</span><span class="o">,</span> <span class="mf">5.0</span><span class="o">),</span> |
| <span class="nc">Vectors</span><span class="o">.</span><span class="na">dense</span><span class="o">(</span><span class="mf">4.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">6.0</span><span class="o">,</span> <span class="mf">7.0</span><span class="o">)</span> |
| <span class="o">);</span> |
| |
| <span class="nc">JavaRDD</span><span class="o"><</span><span class="nc">Vector</span><span class="o">></span> <span class="n">rows</span> <span class="o">=</span> <span class="n">jsc</span><span class="o">.</span><span class="na">parallelize</span><span class="o">(</span><span class="n">data</span><span class="o">);</span> |
| |
| <span class="c1">// Create a RowMatrix from JavaRDD<Vector>.</span> |
| <span class="nc">RowMatrix</span> <span class="n">mat</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">RowMatrix</span><span class="o">(</span><span class="n">rows</span><span class="o">.</span><span class="na">rdd</span><span class="o">());</span> |
| |
| <span class="c1">// Compute the top 5 singular values and corresponding singular vectors.</span> |
| <span class="nc">SingularValueDecomposition</span><span class="o"><</span><span class="nc">RowMatrix</span><span class="o">,</span> <span class="nc">Matrix</span><span class="o">></span> <span class="n">svd</span> <span class="o">=</span> <span class="n">mat</span><span class="o">.</span><span class="na">computeSVD</span><span class="o">(</span><span class="mi">5</span><span class="o">,</span> <span class="kc">true</span><span class="o">,</span> <span class="mf">1.0</span><span class="no">E</span><span class="o">-</span><span class="mi">9</span><span class="n">d</span><span class="o">);</span> |
| <span class="nc">RowMatrix</span> <span class="no">U</span> <span class="o">=</span> <span class="n">svd</span><span class="o">.</span><span class="na">U</span><span class="o">();</span> <span class="c1">// The U factor is a RowMatrix.</span> |
| <span class="nc">Vector</span> <span class="n">s</span> <span class="o">=</span> <span class="n">svd</span><span class="o">.</span><span class="na">s</span><span class="o">();</span> <span class="c1">// The singular values are stored in a local dense vector.</span> |
| <span class="nc">Matrix</span> <span class="no">V</span> <span class="o">=</span> <span class="n">svd</span><span class="o">.</span><span class="na">V</span><span class="o">();</span> <span class="c1">// The V factor is a local dense matrix.</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/java/org/apache/spark/examples/mllib/JavaSVDExample.java" in the Spark repo.</small></div> |
| |
| <p>The same code applies to <code class="language-plaintext highlighter-rouge">IndexedRowMatrix</code> if <code class="language-plaintext highlighter-rouge">U</code> is defined as an |
| <code class="language-plaintext highlighter-rouge">IndexedRowMatrix</code>.</p> |
| </div> |
| |
| </div> |
| |
| <h2 id="principal-component-analysis-pca">Principal component analysis (PCA)</h2> |
| |
| <p><a href="http://en.wikipedia.org/wiki/Principal_component_analysis">Principal component analysis (PCA)</a> is a |
| statistical method to find a rotation such that the first coordinate has the largest variance |
| possible, and each succeeding coordinate, in turn, has the largest variance possible. The columns of |
| the rotation matrix are called principal components. PCA is used widely in dimensionality reduction.</p> |
| |
| <p><code class="language-plaintext highlighter-rouge">spark.mllib</code> supports PCA for tall-and-skinny matrices stored in row-oriented format and any Vectors.</p> |
| |
| <div class="codetabs"> |
| |
| <div data-lang="python"> |
| |
| <p>The following code demonstrates how to compute principal components on a <code class="language-plaintext highlighter-rouge">RowMatrix</code> |
| and use them to project the vectors into a low-dimensional space.</p> |
| |
| <p>Refer to the <a href="api/python/reference/api/pyspark.mllib.linalg.distributed.RowMatrix.html"><code class="language-plaintext highlighter-rouge">RowMatrix</code> Python docs</a> for details on the API.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">from</span> <span class="nn">pyspark.mllib.linalg</span> <span class="kn">import</span> <span class="n">Vectors</span> |
| <span class="kn">from</span> <span class="nn">pyspark.mllib.linalg.distributed</span> <span class="kn">import</span> <span class="n">RowMatrix</span> |
| |
| <span class="n">rows</span> <span class="o">=</span> <span class="n">sc</span><span class="p">.</span><span class="n">parallelize</span><span class="p">([</span> |
| <span class="n">Vectors</span><span class="p">.</span><span class="n">sparse</span><span class="p">(</span><span class="mi">5</span><span class="p">,</span> <span class="p">{</span><span class="mi">1</span><span class="p">:</span> <span class="mf">1.0</span><span class="p">,</span> <span class="mi">3</span><span class="p">:</span> <span class="mf">7.0</span><span class="p">}),</span> |
| <span class="n">Vectors</span><span class="p">.</span><span class="n">dense</span><span class="p">(</span><span class="mf">2.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="mf">3.0</span><span class="p">,</span> <span class="mf">4.0</span><span class="p">,</span> <span class="mf">5.0</span><span class="p">),</span> |
| <span class="n">Vectors</span><span class="p">.</span><span class="n">dense</span><span class="p">(</span><span class="mf">4.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="mf">0.0</span><span class="p">,</span> <span class="mf">6.0</span><span class="p">,</span> <span class="mf">7.0</span><span class="p">)</span> |
| <span class="p">])</span> |
| |
| <span class="n">mat</span> <span class="o">=</span> <span class="n">RowMatrix</span><span class="p">(</span><span class="n">rows</span><span class="p">)</span> |
| <span class="c1"># Compute the top 4 principal components. |
| # Principal components are stored in a local dense matrix. |
| </span><span class="n">pc</span> <span class="o">=</span> <span class="n">mat</span><span class="p">.</span><span class="n">computePrincipalComponents</span><span class="p">(</span><span class="mi">4</span><span class="p">)</span> |
| |
| <span class="c1"># Project the rows to the linear space spanned by the top 4 principal components. |
| </span><span class="n">projected</span> <span class="o">=</span> <span class="n">mat</span><span class="p">.</span><span class="n">multiply</span><span class="p">(</span><span class="n">pc</span><span class="p">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/python/mllib/pca_rowmatrix_example.py" in the Spark repo.</small></div> |
| |
| </div> |
| |
| <div data-lang="scala"> |
| |
| <p>The following code demonstrates how to compute principal components on a <code class="language-plaintext highlighter-rouge">RowMatrix</code> |
| and use them to project the vectors into a low-dimensional space.</p> |
| |
| <p>Refer to the <a href="api/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.html"><code class="language-plaintext highlighter-rouge">RowMatrix</code> Scala docs</a> for details on the API.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Matrix</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.distributed.RowMatrix</span> |
| |
| <span class="k">val</span> <span class="nv">data</span> <span class="k">=</span> <span class="nc">Array</span><span class="o">(</span> |
| <span class="nv">Vectors</span><span class="o">.</span><span class="py">sparse</span><span class="o">(</span><span class="mi">5</span><span class="o">,</span> <span class="nc">Seq</span><span class="o">((</span><span class="mi">1</span><span class="o">,</span> <span class="mf">1.0</span><span class="o">),</span> <span class="o">(</span><span class="mi">3</span><span class="o">,</span> <span class="mf">7.0</span><span class="o">))),</span> |
| <span class="nv">Vectors</span><span class="o">.</span><span class="py">dense</span><span class="o">(</span><span class="mf">2.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">3.0</span><span class="o">,</span> <span class="mf">4.0</span><span class="o">,</span> <span class="mf">5.0</span><span class="o">),</span> |
| <span class="nv">Vectors</span><span class="o">.</span><span class="py">dense</span><span class="o">(</span><span class="mf">4.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">6.0</span><span class="o">,</span> <span class="mf">7.0</span><span class="o">))</span> |
| |
| <span class="k">val</span> <span class="nv">rows</span> <span class="k">=</span> <span class="nv">sc</span><span class="o">.</span><span class="py">parallelize</span><span class="o">(</span><span class="n">data</span><span class="o">)</span> |
| |
| <span class="k">val</span> <span class="nv">mat</span><span class="k">:</span> <span class="kt">RowMatrix</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">RowMatrix</span><span class="o">(</span><span class="n">rows</span><span class="o">)</span> |
| |
| <span class="c1">// Compute the top 4 principal components.</span> |
| <span class="c1">// Principal components are stored in a local dense matrix.</span> |
| <span class="k">val</span> <span class="nv">pc</span><span class="k">:</span> <span class="kt">Matrix</span> <span class="o">=</span> <span class="nv">mat</span><span class="o">.</span><span class="py">computePrincipalComponents</span><span class="o">(</span><span class="mi">4</span><span class="o">)</span> |
| |
| <span class="c1">// Project the rows to the linear space spanned by the top 4 principal components.</span> |
| <span class="k">val</span> <span class="nv">projected</span><span class="k">:</span> <span class="kt">RowMatrix</span> <span class="o">=</span> <span class="nv">mat</span><span class="o">.</span><span class="py">multiply</span><span class="o">(</span><span class="n">pc</span><span class="o">)</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/mllib/PCAOnRowMatrixExample.scala" in the Spark repo.</small></div> |
| |
| <p>The following code demonstrates how to compute principal components on source vectors |
| and use them to project the vectors into a low-dimensional space while keeping associated labels:</p> |
| |
| <p>Refer to the <a href="api/scala/org/apache/spark/mllib/feature/PCA.html"><code class="language-plaintext highlighter-rouge">PCA</code> Scala docs</a> for details on the API.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="k">import</span> <span class="nn">org.apache.spark.mllib.feature.PCA</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.mllib.regression.LabeledPoint</span> |
| <span class="k">import</span> <span class="nn">org.apache.spark.rdd.RDD</span> |
| |
| <span class="k">val</span> <span class="nv">data</span><span class="k">:</span> <span class="kt">RDD</span><span class="o">[</span><span class="kt">LabeledPoint</span><span class="o">]</span> <span class="k">=</span> <span class="nv">sc</span><span class="o">.</span><span class="py">parallelize</span><span class="o">(</span><span class="nc">Seq</span><span class="o">(</span> |
| <span class="k">new</span> <span class="nc">LabeledPoint</span><span class="o">(</span><span class="mi">0</span><span class="o">,</span> <span class="nv">Vectors</span><span class="o">.</span><span class="py">dense</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="mi">0</span><span class="o">,</span> <span class="mi">0</span><span class="o">,</span> <span class="mi">0</span><span class="o">,</span> <span class="mi">1</span><span class="o">)),</span> |
| <span class="k">new</span> <span class="nc">LabeledPoint</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="nv">Vectors</span><span class="o">.</span><span class="py">dense</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="mi">1</span><span class="o">,</span> <span class="mi">0</span><span class="o">,</span> <span class="mi">1</span><span class="o">,</span> <span class="mi">0</span><span class="o">)),</span> |
| <span class="k">new</span> <span class="nc">LabeledPoint</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="nv">Vectors</span><span class="o">.</span><span class="py">dense</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="mi">1</span><span class="o">,</span> <span class="mi">0</span><span class="o">,</span> <span class="mi">0</span><span class="o">,</span> <span class="mi">0</span><span class="o">)),</span> |
| <span class="k">new</span> <span class="nc">LabeledPoint</span><span class="o">(</span><span class="mi">0</span><span class="o">,</span> <span class="nv">Vectors</span><span class="o">.</span><span class="py">dense</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="mi">0</span><span class="o">,</span> <span class="mi">0</span><span class="o">,</span> <span class="mi">0</span><span class="o">,</span> <span class="mi">0</span><span class="o">)),</span> |
| <span class="k">new</span> <span class="nc">LabeledPoint</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="nv">Vectors</span><span class="o">.</span><span class="py">dense</span><span class="o">(</span><span class="mi">1</span><span class="o">,</span> <span class="mi">1</span><span class="o">,</span> <span class="mi">0</span><span class="o">,</span> <span class="mi">0</span><span class="o">,</span> <span class="mi">0</span><span class="o">))))</span> |
| |
| <span class="c1">// Compute the top 5 principal components.</span> |
| <span class="k">val</span> <span class="nv">pca</span> <span class="k">=</span> <span class="k">new</span> <span class="nc">PCA</span><span class="o">(</span><span class="mi">5</span><span class="o">).</span><span class="py">fit</span><span class="o">(</span><span class="nv">data</span><span class="o">.</span><span class="py">map</span><span class="o">(</span><span class="nv">_</span><span class="o">.</span><span class="py">features</span><span class="o">))</span> |
| |
| <span class="c1">// Project vectors to the linear space spanned by the top 5 principal</span> |
| <span class="c1">// components, keeping the label</span> |
| <span class="k">val</span> <span class="nv">projected</span> <span class="k">=</span> <span class="nv">data</span><span class="o">.</span><span class="py">map</span><span class="o">(</span><span class="n">p</span> <span class="k">=></span> <span class="nv">p</span><span class="o">.</span><span class="py">copy</span><span class="o">(</span><span class="n">features</span> <span class="k">=</span> <span class="nv">pca</span><span class="o">.</span><span class="py">transform</span><span class="o">(</span><span class="nv">p</span><span class="o">.</span><span class="py">features</span><span class="o">)))</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/scala/org/apache/spark/examples/mllib/PCAOnSourceVectorExample.scala" in the Spark repo.</small></div> |
| |
| </div> |
| |
| <div data-lang="java"> |
| |
| <p>The following code demonstrates how to compute principal components on a <code class="language-plaintext highlighter-rouge">RowMatrix</code> |
| and use them to project the vectors into a low-dimensional space.</p> |
| |
| <p>Refer to the <a href="api/java/org/apache/spark/mllib/linalg/distributed/RowMatrix.html"><code class="language-plaintext highlighter-rouge">RowMatrix</code> Java docs</a> for details on the API.</p> |
| |
| <div class="highlight"><pre class="codehilite"><code><span class="kn">import</span> <span class="nn">java.util.Arrays</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">java.util.List</span><span class="o">;</span> |
| |
| <span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaRDD</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.api.java.JavaSparkContext</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Matrix</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vector</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.Vectors</span><span class="o">;</span> |
| <span class="kn">import</span> <span class="nn">org.apache.spark.mllib.linalg.distributed.RowMatrix</span><span class="o">;</span> |
| |
| <span class="nc">List</span><span class="o"><</span><span class="nc">Vector</span><span class="o">></span> <span class="n">data</span> <span class="o">=</span> <span class="nc">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span> |
| <span class="nc">Vectors</span><span class="o">.</span><span class="na">sparse</span><span class="o">(</span><span class="mi">5</span><span class="o">,</span> <span class="k">new</span> <span class="kt">int</span><span class="o">[]</span> <span class="o">{</span><span class="mi">1</span><span class="o">,</span> <span class="mi">3</span><span class="o">},</span> <span class="k">new</span> <span class="kt">double</span><span class="o">[]</span> <span class="o">{</span><span class="mf">1.0</span><span class="o">,</span> <span class="mf">7.0</span><span class="o">}),</span> |
| <span class="nc">Vectors</span><span class="o">.</span><span class="na">dense</span><span class="o">(</span><span class="mf">2.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">3.0</span><span class="o">,</span> <span class="mf">4.0</span><span class="o">,</span> <span class="mf">5.0</span><span class="o">),</span> |
| <span class="nc">Vectors</span><span class="o">.</span><span class="na">dense</span><span class="o">(</span><span class="mf">4.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">0.0</span><span class="o">,</span> <span class="mf">6.0</span><span class="o">,</span> <span class="mf">7.0</span><span class="o">)</span> |
| <span class="o">);</span> |
| |
| <span class="nc">JavaRDD</span><span class="o"><</span><span class="nc">Vector</span><span class="o">></span> <span class="n">rows</span> <span class="o">=</span> <span class="n">jsc</span><span class="o">.</span><span class="na">parallelize</span><span class="o">(</span><span class="n">data</span><span class="o">);</span> |
| |
| <span class="c1">// Create a RowMatrix from JavaRDD<Vector>.</span> |
| <span class="nc">RowMatrix</span> <span class="n">mat</span> <span class="o">=</span> <span class="k">new</span> <span class="nc">RowMatrix</span><span class="o">(</span><span class="n">rows</span><span class="o">.</span><span class="na">rdd</span><span class="o">());</span> |
| |
| <span class="c1">// Compute the top 4 principal components.</span> |
| <span class="c1">// Principal components are stored in a local dense matrix.</span> |
| <span class="nc">Matrix</span> <span class="n">pc</span> <span class="o">=</span> <span class="n">mat</span><span class="o">.</span><span class="na">computePrincipalComponents</span><span class="o">(</span><span class="mi">4</span><span class="o">);</span> |
| |
| <span class="c1">// Project the rows to the linear space spanned by the top 4 principal components.</span> |
| <span class="nc">RowMatrix</span> <span class="n">projected</span> <span class="o">=</span> <span class="n">mat</span><span class="o">.</span><span class="na">multiply</span><span class="o">(</span><span class="n">pc</span><span class="o">);</span></code></pre></div> |
| <div><small>Find full example code at "examples/src/main/java/org/apache/spark/examples/mllib/JavaPCAExample.java" in the Spark repo.</small></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| </div> |
| |
| <!-- /container --> |
| </div> |
| |
| <script src="js/vendor/jquery-3.5.1.min.js"></script> |
| <script src="js/vendor/bootstrap.bundle.min.js"></script> |
| |
| <script src="js/vendor/anchor.min.js"></script> |
| <script src="js/main.js"></script> |
| |
| <script type="text/javascript" src="js/vendor/docsearch.min.js"></script> |
| <script type="text/javascript"> |
| // DocSearch is entirely free and automated. DocSearch is built in two parts: |
| // 1. a crawler which we run on our own infrastructure every 24 hours. It follows every link |
| // in your website and extract content from every page it traverses. It then pushes this |
| // content to an Algolia index. |
| // 2. a JavaScript snippet to be inserted in your website that will bind this Algolia index |
| // to your search input and display its results in a dropdown UI. If you want to find more |
| // details on how works DocSearch, check the docs of DocSearch. |
| docsearch({ |
| apiKey: 'd62f962a82bc9abb53471cb7b89da35e', |
| appId: 'RAI69RXRSK', |
| indexName: 'apache_spark', |
| inputSelector: '#docsearch-input', |
| enhancedSearchInput: true, |
| algoliaOptions: { |
| 'facetFilters': ["version:3.5.3"] |
| }, |
| debug: false // Set debug to true if you want to inspect the dropdown |
| }); |
| |
| </script> |
| |
| <!-- MathJax Section --> |
| <script type="text/x-mathjax-config"> |
| MathJax.Hub.Config({ |
| TeX: { equationNumbers: { autoNumber: "AMS" } } |
| }); |
| </script> |
| <script> |
| // Note that we load MathJax this way to work with local file (file://), HTTP and HTTPS. |
| // We could use "//cdn.mathjax...", but that won't support "file://". |
| (function(d, script) { |
| script = d.createElement('script'); |
| script.type = 'text/javascript'; |
| script.async = true; |
| script.onload = function(){ |
| MathJax.Hub.Config({ |
| tex2jax: { |
| inlineMath: [ ["$", "$"], ["\\\\(","\\\\)"] ], |
| displayMath: [ ["$$","$$"], ["\\[", "\\]"] ], |
| processEscapes: true, |
| skipTags: ['script', 'noscript', 'style', 'textarea', 'pre'] |
| } |
| }); |
| }; |
| script.src = ('https:' == document.location.protocol ? 'https://' : 'http://') + |
| 'cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js' + |
| '?config=TeX-AMS-MML_HTMLorMML'; |
| d.getElementsByTagName('head')[0].appendChild(script); |
| }(document)); |
| </script> |
| </body> |
| </html> |
